© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6856
    Prev
    Next
    INDEX
    Explanations

    question-answering or information extraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erythrocytes
    0.54
     fabriqu
    0.46
     assays
    0.45
     theologians
    0.44
     fibroblasts
    0.44
    틸
    0.44
     attorneys
    0.43
    ாளையம்
    0.43
     affirmat
    0.43
     electrolytes
    0.43
    POSITIVE LOGITS
    (
    0.62
    在
    0.55
    .
    0.55
    ​​​​
    0.50
    ​​
    0.47
    รอบ
    0.45
    )，
    0.44
    由
    0.44
     Junio
    0.43
     रहा
    0.43
    Activations Density 0.009%

    No Known Activations